Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2669 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.3547. Min Range: -3.3547

Max Act: 3.3547. Min Act: -0.1700

Data Index: 4957738 (Open Web Text)

Max Activating Token Index: 370

Text #1

Max Range: 3.3547. Min Range: -3.3547

Max Act: 3.3254. Min Act: -0.1700

Data Index: 6175363 (Open Web Text)

Max Activating Token Index: 774

Text #2

Max Range: 3.3547. Min Range: -3.3547

Max Act: 3.3389. Min Act: -0.1700

Data Index: 121515 (Open Web Text)

Max Activating Token Index: 990

Text #3

Max Range: 3.3547. Min Range: -3.3547

Max Act: 3.3022. Min Act: -0.1700

Data Index: 4343816 (Open Web Text)

Max Activating Token Index: 678

Text #4

Max Range: 3.3547. Min Range: -3.3547

Max Act: 3.2889. Min Act: -0.1700

Data Index: 6582899 (Open Web Text)

Max Activating Token Index: 515

Text #5

Max Range: 3.3547. Min Range: -3.3547

Max Act: 3.3030. Min Act: -0.1700

Data Index: 2977508 (Open Web Text)

Max Activating Token Index: 406

Text #6

Max Range: 3.3547. Min Range: -3.3547

Max Act: 3.3025. Min Act: -0.1700

Data Index: 6659225 (Open Web Text)

Max Activating Token Index: 541

Text #7

Max Range: 3.3547. Min Range: -3.3547

Max Act: 3.3001. Min Act: -0.1700

Data Index: 8705206 (Open Web Text)

Max Activating Token Index: 262

Text #8

Max Range: 3.3547. Min Range: -3.3547

Max Act: 3.2982. Min Act: -0.1700

Data Index: 3435317 (Open Web Text)

Max Activating Token Index: 982

Text #9

Max Range: 3.3547. Min Range: -3.3547

Max Act: 3.2700. Min Act: -0.1700

Data Index: 4212985 (Open Web Text)

Max Activating Token Index: 726

Text #10

Max Range: 3.3547. Min Range: -3.3547

Max Act: 3.3140. Min Act: -0.1700

Data Index: 7781818 (Open Web Text)

Max Activating Token Index: 753

Text #11

Max Range: 3.3547. Min Range: -3.3547

Max Act: 3.2696. Min Act: -0.1700

Data Index: 5218345 (Open Web Text)

Max Activating Token Index: 850

Text #12

Max Range: 3.3547. Min Range: -3.3547

Max Act: 3.2602. Min Act: -0.1700

Data Index: 5388348 (Open Web Text)

Max Activating Token Index: 508

Text #13

Max Range: 3.3547. Min Range: -3.3547

Max Act: 3.2513. Min Act: -0.1700

Data Index: 2520341 (Open Web Text)

Max Activating Token Index: 549

Text #14

Max Range: 3.3547. Min Range: -3.3547

Max Act: 3.2627. Min Act: -0.1700

Data Index: 2074423 (Open Web Text)

Max Activating Token Index: 413

Text #15

Max Range: 3.3547. Min Range: -3.3547

Max Act: 3.2430. Min Act: -0.1700

Data Index: 5129360 (Open Web Text)

Max Activating Token Index: 374

Text #16

Max Range: 3.3547. Min Range: -3.3547

Max Act: 3.2506. Min Act: -0.1700

Data Index: 923113 (Open Web Text)

Max Activating Token Index: 942

Text #17

Max Range: 3.3547. Min Range: -3.3547

Max Act: 3.2324. Min Act: -0.1700

Data Index: 2052041 (Open Web Text)

Max Activating Token Index: 708

Text #18

Max Range: 3.3547. Min Range: -3.3547

Max Act: 3.2385. Min Act: -0.1700

Data Index: 3564756 (Open Web Text)

Max Activating Token Index: 820

Text #19

Max Range: 3.3547. Min Range: -3.3547

Max Act: 3.2293. Min Act: -0.1700

Data Index: 333583 (Open Web Text)

Max Activating Token Index: 685